© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12772
    Prev
    Next
    INDEX
    Explanations

    a number accompanied by "single" or "once"

    oai_token-act-pair · gemini-2.0-flash

    one

    np_max-act · gemini-2.0-flash

    one Method used: 1 — because the max-activating tokens are all singular/one variants — one

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessorType
    -0.57
    ThroughAttribute
    -0.56
    Donkey
    -0.55
    >`;
    -0.54
    Насе
    -0.53
    ImageContext
    -0.52
     onCreateView
    -0.50
     viewType
    -0.50
    }))
    -0.50
    waitKey
    -0.47
    POSITIVE LOGITS
     Bourgoin
    0.61
    HasAnnotation
    0.59
     Мексичка
    0.58
    addCriterion
    0.58
    Plural
    0.57
    fetchone
    0.57
    RetentionPolicy
    0.57
    CodedInputStream
    0.56
     nakalista
    0.56
    StoryboardSegue
    0.56
    Activations Density 1.607%

    No Known Activations